{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4010369777679443, "min": 1.4010369777679443, "max": 1.4279608726501465, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 66893.9140625, "min": 66893.9140625, "max": 77328.78125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 119.10791366906474, "min": 94.64435946462716, "max": 380.6212121212121, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49668.0, "min": 49071.0, "max": 50242.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999337.0, "min": 49738.0, "max": 1999337.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999337.0, "min": 49738.0, "max": 1999337.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.302340269088745, "min": 0.008680038154125214, "max": 2.378091812133789, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 960.075927734375, "min": 1.1370849609375, "max": 1207.6920166015625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.5404951342289968, "min": 1.751283003969957, "max": 3.913444149444809, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1476.3864709734917, "min": 229.41807352006435, "max": 1966.310101032257, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.5404951342289968, "min": 1.751283003969957, "max": 3.913444149444809, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1476.3864709734917, "min": 229.41807352006435, "max": 1966.310101032257, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018690276772960916, "min": 0.012564418473796954, "max": 0.020111255764519834, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05607083031888275, "min": 0.025128836947593908, "max": 0.060333767293559507, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.044084138754341334, "min": 0.02101296993593375, "max": 0.07207807538410028, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.132252416263024, "min": 0.0420259398718675, "max": 0.21623422615230087, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.178348940583339e-06, "min": 3.178348940583339e-06, "max": 0.000295269001577, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 9.535046821750017e-06, "min": 9.535046821750017e-06, "max": 0.0008438287687237499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10105941666666667, "min": 0.10105941666666667, "max": 0.19842300000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30317825, "min": 0.20724775, "max": 0.58127625, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.286489166666677e-05, "min": 6.286489166666677e-05, "max": 0.0049213077000000004, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001885946750000003, "min": 0.0001885946750000003, "max": 0.014065684875, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1670851179", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics", "mlagents_version": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1670853392" }, "total": 2212.24891041, "count": 1, "self": 0.38967187699972783, "children": { "run_training.setup": { "total": 0.11127775199997814, "count": 1, "self": 0.11127775199997814 }, "TrainerController.start_learning": { "total": 2211.747960781, "count": 1, "self": 3.9807950619460826, "children": { "TrainerController._reset_env": { "total": 10.020979356999987, "count": 1, "self": 10.020979356999987 }, "TrainerController.advance": { "total": 2197.6317818760544, "count": 231283, "self": 3.9617086070620644, "children": { "env_step": { "total": 1719.914049251014, "count": 231283, "self": 1442.6354788540025, "children": { "SubprocessEnvManager._take_step": { "total": 274.7112381819836, "count": 231283, "self": 14.3986495931141, "children": { "TorchPolicy.evaluate": { "total": 260.3125885888695, "count": 222816, "self": 64.8831556888357, "children": { "TorchPolicy.sample_actions": { "total": 195.42943290003382, "count": 222816, "self": 195.42943290003382 } } } } }, "workers": { "total": 2.567332215027932, "count": 231283, "self": 0.0, "children": { "worker_root": { "total": 2203.937780265882, "count": 231283, "is_parallel": true, "self": 1017.1824911429521, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021917920000760205, "count": 1, "is_parallel": true, "self": 0.0003014940000412025, "children": { "_process_rank_one_or_two_observation": { "total": 0.001890298000034818, "count": 2, "is_parallel": true, "self": 0.001890298000034818 } } }, "UnityEnvironment.step": { "total": 0.026603526999906535, "count": 1, "is_parallel": true, "self": 0.0002856799998198767, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017409800000223186, "count": 1, "is_parallel": true, "self": 0.00017409800000223186 }, "communicator.exchange": { "total": 0.02539183800001865, "count": 1, "is_parallel": true, "self": 0.02539183800001865 }, "steps_from_proto": { "total": 0.0007519110000657747, "count": 1, "is_parallel": true, "self": 0.00028933800001595955, "children": { "_process_rank_one_or_two_observation": { "total": 0.00046257300004981516, "count": 2, "is_parallel": true, "self": 0.00046257300004981516 } } } } } } }, "UnityEnvironment.step": { "total": 1186.7552891229298, "count": 231282, "is_parallel": true, "self": 34.637032786040436, "children": { "UnityEnvironment._generate_step_input": { "total": 75.88306821498645, "count": 231282, "is_parallel": true, "self": 75.88306821498645 }, "communicator.exchange": { "total": 984.9272104729215, "count": 231282, "is_parallel": true, "self": 984.9272104729215 }, "steps_from_proto": { "total": 91.30797764898125, "count": 231282, "is_parallel": true, "self": 37.46673452811274, "children": { "_process_rank_one_or_two_observation": { "total": 53.84124312086851, "count": 462564, "is_parallel": true, "self": 53.84124312086851 } } } } } } } } } } }, "trainer_advance": { "total": 473.75602401797835, "count": 231283, "self": 6.148897882952497, "children": { "process_trajectory": { "total": 139.63319430202807, "count": 231283, "self": 139.15225000302814, "children": { "RLTrainer._checkpoint": { "total": 0.48094429899992974, "count": 4, "self": 0.48094429899992974 } } }, "_update_policy": { "total": 327.9739318329978, "count": 97, "self": 273.91548920499974, "children": { "TorchPPOOptimizer.update": { "total": 54.05844262799803, "count": 2910, "self": 54.05844262799803 } } } } } } }, "trainer_threads": { "total": 8.889996934158262e-07, "count": 1, "self": 8.889996934158262e-07 }, "TrainerController._save_models": { "total": 0.11440359699963665, "count": 1, "self": 0.0019003569996129954, "children": { "RLTrainer._checkpoint": { "total": 0.11250324000002365, "count": 1, "self": 0.11250324000002365 } } } } } } }